AutoML Leaderboard

Best model	name	model_type	metric_type	metric_value	train_time
	1_Baseline	Baseline	auc	0.5	0.97
	2_DecisionTree	Decision Tree	auc	0.686825	8.39
	3_Default_Xgboost	Xgboost	auc	0.721372	34.39
the best	4_Default_NeuralNetwork	Neural Network	auc	0.730194	3.93
	5_Default_RandomForest	Random Forest	auc	0.720098	13.74
	Ensemble	Ensemble	auc	0.730194	0.78

AutoML Performance

AutoML Performance Boxplot

Features Importance

Spearman Correlation of Models

Summary of 4_Default_NeuralNetwork

<< Go back

Neural Network

• n_jobs: -1
• dense_1_size: 32
• dense_2_size: 16
• learning_rate: 0.05
• explain_level: 2

Validation

• validation_type: split
• train_ratio: 0.75
• shuffle: True
• stratify: True

Optimized metric

auc

Training time

3.1 seconds

Metric details

	score	threshold
logloss	0.615462	nan
auc	0.730194	nan
f1	0.702065	0.398721
accuracy	0.67325	0.492145
precision	0.804054	0.747265
recall	1	0.102519
mcc	0.346372	0.492145

Metric details with threshold from accuracy metric

	score	threshold
logloss	0.615462	nan
auc	0.730194	nan
f1	0.667479	0.492145
accuracy	0.67325	0.492145
precision	0.662636	0.492145
recall	0.672393	0.492145
mcc	0.346372	0.492145

Confusion matrix (at threshold=0.492145)

	Predicted as 0	Predicted as 1
Labeled as 0	1154	558
Labeled as 1	534	1096

Learning curves

Permutation-based Importance

Confusion Matrix

Normalized Confusion Matrix

ROC Curve

Kolmogorov-Smirnov Statistic

Precision-Recall Curve

Calibration Curve

Cumulative Gains Curve

Lift Curve

<< Go back

Summary of 3_Default_Xgboost

<< Go back

Extreme Gradient Boosting (Xgboost)

• n_jobs: -1
• objective: binary:logistic
• eta: 0.075
• max_depth: 6
• min_child_weight: 1
• subsample: 1.0
• colsample_bytree: 1.0
• eval_metric: auc
• explain_level: 2

Validation

• validation_type: split
• train_ratio: 0.75
• shuffle: True
• stratify: True

Optimized metric

auc

Training time

33.4 seconds

Metric details

	score	threshold
logloss	0.620592	nan
auc	0.721372	nan
f1	0.698278	0.287711
accuracy	0.667265	0.45093
precision	0.77551	0.821216
recall	1	0.019132
mcc	0.339974	0.428066

Metric details with threshold from accuracy metric

	score	threshold
logloss	0.620592	nan
auc	0.721372	nan
f1	0.67712	0.45093
accuracy	0.667265	0.45093
precision	0.642778	0.45093
recall	0.715337	0.45093
mcc	0.337971	0.45093

Confusion matrix (at threshold=0.45093)

	Predicted as 0	Predicted as 1
Labeled as 0	1064	648
Labeled as 1	464	1166

Learning curves

Permutation-based Importance

Confusion Matrix

Normalized Confusion Matrix

ROC Curve

Kolmogorov-Smirnov Statistic

Precision-Recall Curve

Calibration Curve

Cumulative Gains Curve

Lift Curve

SHAP Importance

SHAP Dependence plots

Dependence (Fold 1)

SHAP Decision plots

<< Go back

Summary of 1_Baseline

<< Go back

Baseline Classifier (Baseline)

• n_jobs: -1
• explain_level: 2

Validation

• validation_type: split
• train_ratio: 0.75
• shuffle: True
• stratify: True

Optimized metric

auc

Training time

0.3 seconds

Metric details

	score	threshold
logloss	0.692846	nan
auc	0.5	nan
f1	0.655672	0.439048
accuracy	0.487732	0.439048
precision	0.487732	0.439048
recall	1	0.439048
mcc	0	0.439048

Metric details with threshold from accuracy metric

	score	threshold
logloss	0.692846	nan
auc	0.5	nan
f1	0.655672	0.439048
accuracy	0.487732	0.439048
precision	0.487732	0.439048
recall	1	0.439048
mcc	0	0.439048

Confusion matrix (at threshold=0.439048)

	Predicted as 0	Predicted as 1
Labeled as 0	0	1712
Labeled as 1	0	1630

Learning curves

Confusion Matrix

Normalized Confusion Matrix

ROC Curve

Kolmogorov-Smirnov Statistic

Precision-Recall Curve

Calibration Curve

Cumulative Gains Curve

Lift Curve

<< Go back

Summary of Ensemble

<< Go back

Ensemble structure

Model	Weight
4_Default_NeuralNetwork	1

Metric details

	score	threshold
logloss	0.615462	nan
auc	0.730194	nan
f1	0.702065	0.398721
accuracy	0.67325	0.492145
precision	0.804054	0.747265
recall	1	0.102519
mcc	0.346372	0.492145

Metric details with threshold from accuracy metric

	score	threshold
logloss	0.615462	nan
auc	0.730194	nan
f1	0.667479	0.492145
accuracy	0.67325	0.492145
precision	0.662636	0.492145
recall	0.672393	0.492145
mcc	0.346372	0.492145

Confusion matrix (at threshold=0.492145)

	Predicted as 0	Predicted as 1
Labeled as 0	1154	558
Labeled as 1	534	1096

Learning curves

Confusion Matrix

Normalized Confusion Matrix

ROC Curve

Kolmogorov-Smirnov Statistic

Precision-Recall Curve

Calibration Curve

Cumulative Gains Curve

Lift Curve

<< Go back

Summary of 2_DecisionTree

<< Go back

Decision Tree

• n_jobs: -1
• criterion: gini
• max_depth: 3
• explain_level: 2

Validation

• validation_type: split
• train_ratio: 0.75
• shuffle: True
• stratify: True

Optimized metric

auc

Training time

7.4 seconds

Metric details

	score	threshold
logloss	0.636107	nan
auc	0.686825	nan
f1	0.685212	0.360543
accuracy	0.645123	0.393044
precision	0.688312	0.64668
recall	1	0.119135
mcc	0.290289	0.393044

Metric details with threshold from accuracy metric

	score	threshold
logloss	0.636107	nan
auc	0.686825	nan
f1	0.640388	0.393044
accuracy	0.645123	0.393044
precision	0.633094	0.393044
recall	0.647853	0.393044
mcc	0.290289	0.393044

Confusion matrix (at threshold=0.393044)

	Predicted as 0	Predicted as 1
Labeled as 0	1100	612
Labeled as 1	574	1056

Learning curves

Permutation-based Importance

Confusion Matrix

Normalized Confusion Matrix

ROC Curve

Kolmogorov-Smirnov Statistic

Precision-Recall Curve

Calibration Curve

Cumulative Gains Curve

Lift Curve

SHAP Importance

<< Go back

Summary of 5_Default_RandomForest

<< Go back

Random Forest

• n_jobs: -1
• criterion: gini
• max_features: 0.9
• min_samples_split: 30
• max_depth: 4
• eval_metric_name: auc
• explain_level: 2

Validation

• validation_type: split
• train_ratio: 0.75
• shuffle: True
• stratify: True

Optimized metric

auc

Training time

12.7 seconds

Metric details

	score	threshold
logloss	0.614998	nan
auc	0.720098	nan
f1	0.697663	0.339689
accuracy	0.663674	0.463685
precision	0.782828	0.756028
recall	1	0.0893927
mcc	0.332139	0.435307

Metric details with threshold from accuracy metric

	score	threshold
logloss	0.614998	nan
auc	0.720098	nan
f1	0.669217	0.463685
accuracy	0.663674	0.463685
precision	0.6431	0.463685
recall	0.697546	0.463685
mcc	0.329428	0.463685

Confusion matrix (at threshold=0.463685)

	Predicted as 0	Predicted as 1
Labeled as 0	1081	631
Labeled as 1	493	1137

Learning curves

Permutation-based Importance

Confusion Matrix

Normalized Confusion Matrix

ROC Curve

Kolmogorov-Smirnov Statistic

Precision-Recall Curve

Calibration Curve

Cumulative Gains Curve

Lift Curve

SHAP Importance

SHAP Dependence plots

Dependence (Fold 1)

SHAP Decision plots

<< Go back